Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b44949483ec3cccd453009b8a931ee397b367ac4be5b5290c988a9d8f814cf7b
+oid sha256:6f222a1c4c489c9c91998165385fa6a8cca4505ef6b72b83a29f1ef9b4476dbd
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b45637c79aceb197c2110c360d9bc99547e45026ae009504f16482a5645c597
+oid sha256:16a7f682e8fe380804a7b69db82778ae81724f76d4bbc7ccc21b9a05753f5bed
 size 1001863522

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8caba3b93c1fca21e02716a300fe85b7e6af05e6408b152c3c1d9bf59a33f384
+oid sha256:8f32b24a025fd99a4774f254c729e6ea1d6653f5243edf7a461d966c3f9cfc90
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d880b962891181a5439d8f93c856ab76db6c44b6450373af2b908ff6f4ffee1
+oid sha256:23001c42c640f89983758733dcfdb4e7daf6cce5a119ac7170fe88dbd18dd1b0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0fc268fa2a0d146134555a885ffa98a1736654f4e6c55b5ebcc44a1dad37908
+oid sha256:1308bf92867c81ae09e5cb48fdc76fbfd6e32eecfad5332d4defae3a6af04703
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecc14669f0af0349fed74e52a76d4aae2bca1d0f966526c5fce3456bc2741c5d
+oid sha256:676b7abf3456dcac426c8247f8ccdff0071875ec709c89ea4a819a457a82dd55
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4496269226074219,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.11074197120708748,
+  "best_metric": 0.3135169446468353,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.22148394241417496,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 25.394,
       "eval_steps_per_second": 3.189,
       "step": 25
+    },
+    {
+      "epoch": 0.11517165005537099,
+      "grad_norm": 43.56239318847656,
+      "learning_rate": 5e-05,
+      "loss": 8.002,
+      "step": 26
+    },
+    {
+      "epoch": 0.11960132890365449,
+      "grad_norm": 42.219730377197266,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 7.7278,
+      "step": 27
+    },
+    {
+      "epoch": 0.12403100775193798,
+      "grad_norm": 51.25581741333008,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 7.8858,
+      "step": 28
+    },
+    {
+      "epoch": 0.12846068660022147,
+      "grad_norm": 28.833730697631836,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 7.4616,
+      "step": 29
+    },
+    {
+      "epoch": 0.132890365448505,
+      "grad_norm": 36.36983108520508,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 5.8613,
+      "step": 30
+    },
+    {
+      "epoch": 0.13732004429678848,
+      "grad_norm": 24.915283203125,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 6.0989,
+      "step": 31
+    },
+    {
+      "epoch": 0.14174972314507198,
+      "grad_norm": 26.047985076904297,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 5.5893,
+      "step": 32
+    },
+    {
+      "epoch": 0.1461794019933555,
+      "grad_norm": 17.464637756347656,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 5.6094,
+      "step": 33
+    },
+    {
+      "epoch": 0.150609080841639,
+      "grad_norm": 19.809972763061523,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 5.3021,
+      "step": 34
+    },
+    {
+      "epoch": 0.15503875968992248,
+      "grad_norm": 29.769086837768555,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 5.5138,
+      "step": 35
+    },
+    {
+      "epoch": 0.15946843853820597,
+      "grad_norm": 25.799795150756836,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 4.979,
+      "step": 36
+    },
+    {
+      "epoch": 0.1638981173864895,
+      "grad_norm": 25.358388900756836,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.709,
+      "step": 37
+    },
+    {
+      "epoch": 0.16832779623477298,
+      "grad_norm": 26.125646591186523,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.5807,
+      "step": 38
+    },
+    {
+      "epoch": 0.17275747508305647,
+      "grad_norm": 20.812122344970703,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 6.1171,
+      "step": 39
+    },
+    {
+      "epoch": 0.17718715393134,
+      "grad_norm": 20.470781326293945,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 6.5875,
+      "step": 40
+    },
+    {
+      "epoch": 0.18161683277962348,
+      "grad_norm": 17.11683464050293,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 6.203,
+      "step": 41
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "grad_norm": 15.608457565307617,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 4.9995,
+      "step": 42
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 14.48198127746582,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 5.2074,
+      "step": 43
+    },
+    {
+      "epoch": 0.19490586932447398,
+      "grad_norm": 17.412363052368164,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 5.2764,
+      "step": 44
+    },
+    {
+      "epoch": 0.19933554817275748,
+      "grad_norm": 26.537670135498047,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 5.5755,
+      "step": 45
+    },
+    {
+      "epoch": 0.20376522702104097,
+      "grad_norm": 25.966537475585938,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 5.1873,
+      "step": 46
+    },
+    {
+      "epoch": 0.2081949058693245,
+      "grad_norm": 19.112852096557617,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 5.2322,
+      "step": 47
+    },
+    {
+      "epoch": 0.21262458471760798,
+      "grad_norm": 19.956279754638672,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 5.3597,
+      "step": 48
+    },
+    {
+      "epoch": 0.21705426356589147,
+      "grad_norm": 26.704853057861328,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 4.1194,
+      "step": 49
+    },
+    {
+      "epoch": 0.22148394241417496,
+      "grad_norm": 22.032495498657227,
+      "learning_rate": 0.0,
+      "loss": 3.1469,
+      "step": 50
+    },
+    {
+      "epoch": 0.22148394241417496,
+      "eval_loss": 0.3135169446468353,
+      "eval_runtime": 59.89,
+      "eval_samples_per_second": 25.397,
+      "eval_steps_per_second": 3.189,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.102842054443008e+17,
+  "total_flos": 1.0205684108886016e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null